Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (non-readonly, non-destructive, non-idempotent), and the description adds real value beyond them: emails are lower-cased, addresses must be unique per audience, and a `full_access` API key is required. These are exactly the preconditions an agent needs before calling a mutating write.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, front-loaded sentences with no filler: the action first, then constraints, then auth/endpoint metadata. The endpoint and operationId are slightly internal but cheap and useful for an API-backed tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter mutation with zero schema description coverage and no output schema, the description omits what the optional fields mean, what is returned (e.g. the created contact or an ID), and what happens on the duplicate-email collision beyond that it 'can only appear once'. That is a meaningful gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden for all five parameters, but it only touches email normalization and says nothing about first_name, last_name, unsubscribed, or the audience_id UUID format. The agent gets types and maxLength from the schema but no semantic guidance from the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb and resource ('Create a contact'), and the API endpoint plus operationId make the operation unambiguous. It doesn't explicitly name a sibling like update_contact, but 'create' vs 'update'/'delete' is clear enough from the name and verb.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the agent must infer that this is for adding a new contact rather than updating an existing one. The uniqueness rule ('An address can only appear once per audience') hints at failure conditions, not at when to prefer create_contact over update_contact, and no exclusions or alternatives are named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.